Bump max number of threads to 1024

app.py

@@ -1,6 +1,7 @@
 import json
 from collections import deque
 from dataclasses import dataclass
+import threading
 from typing import Optional
 
 import gradio as gr
@@ -32,6 +33,7 @@ def get_initial_state() -> GenerationState:
 
 def load_initial_state(request: gr.Request) -> GenerationState:
     print("Loading initial state for", request.client.host)
+    print("Total number of active threads", threading.active_count())
 
     return get_initial_state()
 
@@ -200,4 +202,4 @@ with gr.Blocks(css="style.css", title=f"Realtime Latent Consistency Model") as d
     gr.Examples(examples=EXAMPLES, inputs=[prompt_box], label="Examples")
 
 if __name__ == "__main__":
-    demo.queue(concurrency_count=20, api_open=False).launch(max_threads=64)
+    demo.queue(concurrency_count=20, api_open=False).launch(max_threads=1024)